The proposed method improves localization robustness while maintaining the lightweight and real-time characteristics of YOLOv8n by introducing the outlier degree and a dynamic non-monotonic focusing mechanism.
Abstract
[Objective] To address blurred object boundaries, difficult small-target localization, and unstable bounding-box regression caused by low-quality samples in infrared images of substation electrical equipment, an infrared object detection method based on YOLOv8n improved with Wise-IoU is proposed. [Method] The lightweight YOLOv8n is adopted as the baseline detector, and the original bounding-box regression loss is replaced by Wise-IoU without changing the inference structure. By introducing the outlier degree and a dynamic non-monotonic focusing mechanism, Wise-IoU adaptively adjusts the gradient contribution of samples with different qualities, emphasizes ordinary-quality samples with effective learning value, and suppresses redundant optimization of high-quality samples as well as harmful gradients from low-quality samples. [Result & Conclusion] Experiments on a self-built infrared image dataset of 12 classes of substation electrical equipment show that the YOLOv8n-WIoU model achieves 81.6% mAP@0.5 on the test set, outperforming the baseline YOLOv8n by 6.5 percentage points. Since Wise-IoU only affects the training loss and does not change the network structure during inference, the proposed method improves localization robustness while maintaining the lightweight and real-time characteristics of YOLOv8n.
An SP-YOLO insulator defect detection algorithm based on an improved YOLOv11n model that attains the highest mAP@0.5 and recall among the compared methods while achieving competitive precision, achieving a favorable balance between accuracy and lightweight design.
Yi-Mang Li, Hao-Yu Wang, Jin Liu et al.· Applied Sciences· 0 citations
Reliable detection of Personal Protective Equipment (PPE) in underground mines is a key enabler of automated safety monitoring, and it is also one of the hardest small-object problems in industrial computer vision: helmets, ear-defenders, dust masks, eye-shields and reflective vests occupy only a tiny fraction of the i...
T. Saidani, Refka Ghodhbani, Yahia F. Said· International Journal of Adv...· 0 citations
The future of the field lies in the transition from single-modality visual perception to multi-dimensional collaborative detection systems, and this review serves as a comprehensive reference for optimizing object detection algorithms tailored for complex remote sensing and low-altitude security environments.
Ke Gu· Computer Vision, Graphics an...· 0 citations
Experimental results indicate that BOM-YOLOv12n can serve as a competitive and efficient solution for real-time protective equipment detection in smart construction sites.
An improved algorithm based on RT-DETR is proposed, which achieves a 4.7% improvement in mAP50 on the DOTA dataset, with its computational cost reduced to 40.2 GFLOPs, thereby significantly enhancing both detection efficiency and accuracy.
Rui Zhang, Hao Rao· Conference on Advanced Algor...· 0 citations
This paper proposes an attention-enhanced lightweight adaptive convolutional network (AE-LACNet) to address the challenges of small target recognition, weak anti-interference capability in complex environments, and high deployment costs in power equipment defect detection. The algorithm dynamically matches multi-scale...
Rui-Qi Li, Yong-Jiao Yang, Jia-Xin Lin et al.· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.